© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 146680
    Prev
    Next
    INDEX
    Explanations

    depth of field

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     depart
    0.79
    ходя
    0.78
     элемента
    0.74
     addr
    0.73
     bü
    0.73
    ﾂ
    0.73
    櫛
    0.72
     ওঠার
    0.71
     relo
    0.71
     আত্মীয়
    0.70
    POSITIVE LOGITS
    neither
    0.66
     scanned
    0.65
    nrow
    0.65
    ėje
    0.65
    䐪
    0.63
    洨
    0.63
     isotropy
    0.63
    ProgressListener
    0.62
    plane
    0.62
     शिश
    0.62
    Activations Density 0.001%

    No Known Activations